Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    bullet points or lists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orig
    -0.14
    uben
    -0.14
     Oversight
    -0.14
     Controls
    -0.14
    ollah
    -0.13
    ë¨
    -0.13
     residence
    -0.13
    ÑĨей
    -0.12
     hits
    -0.12
     Sach
    -0.12
    POSITIVE LOGITS
    ERTICAL
    0.16
    å²³
    0.16
    zik
    0.15
    ISIBLE
    0.15
    usher
    0.14
    åĹ
    0.14
     wink
    0.14
    sdale
    0.14
    ysl
    0.14
     onView
    0.14
    Act Density 0.011%

    No Known Activations